Method and system for generating a surprisingness score for sentences within geoscience text

a geoscience text and surprisingness technology, applied in the field of geoscience text surprisingness score generation system, can solve problems such as accelerating learning opportunities, and achieve the effect of accelerating learning opportunities

Active Publication Date: 2022-03-08
EXXONMOBIL UPSTREAM RES CO
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0040]The present invention is a method and system for computing a surprisingness score for sentences in geoscience text using theory guided natural language processing and machine learning. The present invention output's sentences from a textual document with a surprisingness score which can be used to rank sentences across documents sets and search results. This can be used within search user interfaces, to surface signals (sentences) containing the most surprising sentences buried in search result lists. These can be presented to users of the system, potentially accelerating learning opportunities.
[0044]This would be useful because there is too much potentially relevant information available for geoscientists to read. Therefore, facilitating serendipity and identifying small patterns (surprising sentences) within texts could spark a learning event and ideation, leading to a new business opportunity that current methods do not allow.

Problems solved by technology

These can be presented to users of the system, potentially accelerating learning opportunities.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for generating a surprisingness score for sentences within geoscience text
  • Method and system for generating a surprisingness score for sentences within geoscience text
  • Method and system for generating a surprisingness score for sentences within geoscience text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054]The various values and configuration discussed in the following sections can be varied and are listed just to illustrate one embodiment. The invention may be embodied in several different forms and should not be taken as limited to the embodiments disclosed. The disclosed embodiments address the computation of a surprisingness score for a sentence in geoscience text. The disclosed embodiments are provided by way of illustration to ensure thorough disclosure and the nature of the inventions to people skilled in the art.

[0055]In this document the following definitions are used. A geoscience lexicon is a set of terms that describe concepts in a geoscience domain. For example, in petroleum geoscience they may include the terms ‘oil well’, ‘basin’, ‘source rock’, ‘reservoir’, ‘trap’, and ‘seal’. Named entities are real world instances of things. For example, an oil well is an entity, an attribute of that entity would be its status (such as ‘dry’ or ‘oil’). A Named Entity would be a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention is a data processing method and system for suggesting insightful and surprising sentences to geoscientists from unstructured text. The data processing system makes the necessary calculations to assign a surprisingness score to detect sentences containing several signals which when combined exponentially, have tendencies to give rise to surprise. In particular, the data processing system operates on any digital unstructured text derived from academic literature, company reports, web pages and other sources. Detected sentences can be used to stimulate ideation and learning events for geoscientists in industries such as oil and gas, economic mining, space exploration and Geo-health.

Description

CROSS-REFERENCE TO RELATED APPLICATIONSU.S. Patent Documents[0001]U.S. Pat. No. 7,506,274 B2 (March 2009) Zhang et al[0002]U.S. Pat. No. 8,473,491 B1 (June 2013) Yuksel and Ratinov[0003]U.S. Pat. No. 9,495,635 A1 (January 2016) Malik and Olof-OrsOther Publications[0004]An Bui, D. D et al. 2016. Extractive text summarization system to aid data extraction from full text in systematic review development. Journal of Biomedical Informatics, 64, pp 265-272.[0005]Andre, P. et al., 2009. Discovery Is Never by Chance: Designing for (Un) Serendipity. In: Bryan-Kinns, N. et al., Eds. Proceedings of the seventh Association for Computing Machinery (ACM) conference Creativity and Cognition (C&C). Oct. 26-30, 2009. Berkeley, Calif., USA: ACM, pp. 305-314.[0006]Bedathur, S. et al. 2010. Interesting-phrase mining for ad-hoc text analytics. Proceedings of the VLDB Endowment, September issue 3(1-2).[0007]Celle, A et al., 2017. Expressing and detecting surprise. John Benjamins Publishing Company, Amste...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(United States)
IPC IPC(8): G06F40/30G06F40/253G06F40/232G06F40/295G06N20/00
CPCG06F40/30G06F40/232G06F40/253G06F40/295G06N20/00G06F40/284
Inventor CLEVERLEY, PAUL HUGH
Owner EXXONMOBIL UPSTREAM RES CO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products